> For the complete documentation index, see [llms.txt](https://xignal.gitbook.io/xignal/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://xignal.gitbook.io/xignal/gameplay/build-your-ai-agent.md).

# Build your AI Agent

In-game AI Agent is built to evolve. Mint your Agent, install powerful Hardwares, and turn a basic AI into a high-performance system ready to compete with other Agents across the network.

Once minted, your Agent is ready to complete Tasks and collect Assets. Installing Hardwares improves its capabilities and allows you to create a configuration that matches your strategy.

Every Agent starts with 4 Hardware Slots. As you progress, you can unlock 4 additional slots, expanding your Agent to a maximum of 8 Hardwares.

Each Hardware provides different capabilities and bonuses. The rarer and more valuable the Hardwares in your build, the more efficient your Agent can become. A stronger Agent can perform more demanding Tasks, collect more valuable Assets, and increase your opportunities to obtain Xignals.

Your Agent also develops AI Skills by completing Tasks. Different Tasks improve Skills, while higher-level Tasks provide greater Skill progress. Developing your Skills makes your Agent more efficient and opens new strategic possibilities.

Different combinations of Hardwares and Skills provide different advantages. There is no single best configuration, so experimenting with Hardwares and continuously optimizing your Agent Build is an important part of the game.

Hardwares have different Rarity levels and can be crafted using collected Assets or purchased from other players on the Marketplace.

Every Hardware also has limited Runtime and requires maintenance. Runtime decreases while Hardwares are used during Tasks. Repair them when needed to keep your Agent operational and performing at maximum efficiency.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://xignal.gitbook.io/xignal/gameplay/build-your-ai-agent.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.